Daniel Haider

According to our database, Daniel Haider authored at least 13 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Aliasing in Convnets: A Frame-Theoretic Perspective.

Daniel Haider, Vincent Lostanlen, Martin Ehler, Nicki Holighaus, Peter Balazs

CoRR, July, 2025

ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration.

Daniel Haider, Felix Perfler, Peter Balazs, Clara Hollomey, Nicki Holighaus

CoRR, May, 2025

Optimal lower Lipschitz bounds for ReLU layers, saturation, and phase retrieval.

Daniel Freeman, Daniel Haider

CoRR, February, 2025

Residual Hybrid Filterbanks.

Vincent Lostanlen, Xiran Zhang, Daniel Haider, Mathieu Lagrange, Martin Ehler, Peter Balazs

Proceedings of the IEEE Statistical Signal Processing Workshop, 2025

2024

Instabilities in Convnets for Raw Audio.

Daniel Haider, Vincent Lostanlen, Martin Ehler, Péter Balázs

IEEE Signal Process. Lett., 2024

(Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Number.

Rossen Nenov, Daniel Haider, Peter Balazs

CoRR, 2024

Injectivity of ReLU-layers: Perspectives from Frame Theory.

Daniel Haider, Martin Ehler, Péter Balázs

CoRR, 2024

Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement.

Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler, Peter Balazs

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Invertibility of ReLU-Layers: A Practical Approach.

Hannah Eckert, Daniel Haider, Martin Ehler, Peter Balazs

Proceedings of the 16th International Joint Conference on Computational Intelligence, 2024

2023

Energy Preservation and Stability of Random Filterbanks.

Daniel Haider, Vincent Lostanlen, Martin Ehler, Péter Balázs

CoRR, 2023

Fitting Auditory Filterbanks with Multiresolution Neural Networks.

Vincent Lostanlen, Daniel Haider, Han Han, Mathieu Lagrange, Péter Balázs, Martin Ehler

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2023

Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction.

Daniel Haider, Martin Ehler, Péter Balázs

Proceedings of the International Conference on Machine Learning, 2023

2021

Phase-Based Signal Representations for Scattering.

Daniel Haider, Péter Balázs, Nicki Holighaus

Proceedings of the 29th European Signal Processing Conference, 2021